Julen Urain and Jan Peters, representatives from the Technische Universität Darmstadt, participated at the International Conference on Intelligent Robots and Systems (IROS) which took place in Macau, China, on 4-8 of November 2019.
During the conference, they presented the paper “Generalized Multiple Correlation Coefficient as a Similarity Measurement between Trajectories” in a session under the block “Gesture, Posture and Facial Expressions”.
The paper introduces a new correlation metric that presents the best properties to compute similarities between trajectories invariant to linear transformations and compare it with some state-of-the-art similarity distances. On the other hand, the paper presents a natural way of integrating the similarity metric in an imitation learning scenario for clustering robot trajectories.
The IROS Conference aims to present and discuss state-of-the-art concepts for novel research results original perspectives on future developments, and innovative applications relevant to intelligent robots and smart machines. IROS 2019 included plenary and keynote talks, a wide variety of workshops and tutorials, as well as technical sessions and forums.